“Model inference”

Studio-quality music production with multi-pass K3 inference pipeline.

Reverse-engineering a Sketch file (or Figma export with similar shape) into pixel-perfect React + CSS — the iteration mental model, tree reconstruction…

Coding agent that runs fully in the browser on WebGPU, with a local MiniCPM5-2B model and a virtual shell workspace.

AI cloud platform for training, fine-tuning and serving models on on-demand, reserved and private GPU capacity.

LLM workloads on open-source Ray (pinned to 2.57) — OpenAI-compatible serving with ray.serve.llm (vLLM-backed LLMConfig + build_openai_app) and batch…

Build a feature store using Feast for centralized feature management, configure offline and online stores for batch and real-time serving, define feature…

Guide DeepMedic 0.8.4 workflows for multi-modal 3D NIFTI medical-image segmentation, including data preparation, model configuration, training, checkpoint…

Bayesian modeling with PyMC.

MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding.

Use LM Studio as a local LLM backend with Pydantic AI for structured output extraction.

Economic analysis including econometrics, causal inference, time series economics, game theory, welfare analysis, and economic modeling.

Model router that predicts which LLM to call for each request, aimed at cutting coding-agent costs.

Fireworks AI MCP by usefulapi

usefulapi.io

Inspect Fireworks AI models, deployments, datasets and fine-tuning jobs.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching.

Infer integer allele-specific copy number, tumor purity, and ploidy from tumor sequencing by jointly modeling read depth (logR) and B-allele frequency (BAF)…

Shared reference for the Music Assistant local API — base URL, auth, the WebSocket command bus, the DSP/EQ schema, and the data-storage layout this plugin uses.

Route prediction and forecasting problems to the right method.

This skill covers Bayesian estimation and inference in quantitative social science.

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.

The global price benchmark for AI inference: 23 price indexes, market KPIs and SKU-level prices.

Repository operating skill for using Flow Forecast's flood_forecast package for time-series forecasting, data preparation, training, inference, evaluation…

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference…

Source-of-truth reference for the Crusoe x Cerebral Valley "Recursive Agents Hackathon" (Sat Oct 17, 2026, San Francisco) and for building on Crusoe Managed…